Posttranslational modifications of proteins are key features in the identification of CSF biomarkers of multiple sclerosis

Table 3 Sample classification after LDA to discriminate between CSF samples from patients with Relapse–remitting multiple sclerosis (RRMS) and other inflammatory diseases of the CNS (INF)

	Disease	Predicted Group Membership^b.c		Total
	Disease	RRMS	INF	Total
Original
Count	RRMS	68	1	69
Count	INF	2	25	27
%	RRMS	98.6	1.4	100
%	INF	7.4	92.6	100
Cross-validated^a
Count	RRMS	67	2	69
Count	INF	2	25	27
%	RRMS	97.1	2.9	100
%	INF	7.4	92.6	100

^aCross-validation is done only for those sets of samples analyzed. In cross-validation, each sample is classified by the functions derived from all samples other the one under analysis
^b96.9% of original grouped samples correctly classified
^c95.8% of cross-validated grouped samples correctly classified

ISSN: 1742-2094